2 papers
cs.CV2018
Unsupervised Deep Multi-focus Image Fusion
Xiang Yan, Syed Zulqarnain Gilani, Hanlin Qin +1
Convolutional neural networks have recently been used for multi-focus image fusion. However, due to the lack of labeled data for supervised training of such networks, existing meth…
cs.CV2018
Deep Keyframe Detection in Human Action Videos
Xiang Yan, Syed Zulqarnain Gilani, Hanlin Qin +3
Detecting representative frames in videos based on human actions is quite challenging because of the combined factors of human pose in action and the background. This paper address…